© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126953
    Prev
    Next
    INDEX
    Explanations

    mathematical equation

    np_max-act · gemini-2.0-flash

    The neuron detects LaTeX-style equation labels or references (e.g. “\label{…}”, “eq”, and surrounding braces).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concepts
    -0.07
     CDN
    -0.07
     мед
    -0.07
    KD
    -0.07
     ------>
    -0.07
    rod
    -0.06
    _CE
    -0.06
     Solic
    -0.06
     COS
    -0.06
     validated
    -0.06
    POSITIVE LOGITS
    แบบ
    0.06
    stopped
    0.06
    /gen
    0.06
     ovar
    0.06
    .Role
    0.06
     طبقه
    0.06
    lide
    0.05
     seçenek
    0.05
    _export
    0.05
    OptionsResolver
    0.05
    Activations Density 0.001%

    No Known Activations